B-REASO: A Multi-Level Multi-Faceted Bengali Evaluation Suite for Foundation Models, EMNLP Findings 2025 — introduced a Bengali benchmark with 13,497 multiple-choice questions across 50 subjects and 4 difficulty levels
Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?, ACL SRW 2025 — presented a benchmark comprising ICPC World Finals, Continental, and Regional programming contest problems
𝕏olver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team, arXiv preprint 2025 — proposed a training-free multi-agent reasoning framework with persistent, evolving holistic memory for black-box LLMs
Multimodal Programming in Computer Science with Interactive Assistance Powered by Large Language Model, HCII 2025 — developed an interactive homework assistance system for introductory CS programming students
A Hybrid Self Attentive Linearized Phrase Structured Transformer based RNN for Financial Sentence Analysis with Sentence Level Explainability, Scientific Reports 2025 — introduced an interpretable attention-based RNN for financial sentence sentiment analysis